# AgentScope Sample Agents [![All Contributors](https://img.shields.io/badge/all_contributors-8-orange.svg?style=flat-square)](#contributors-) [![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](https://github.com/agentscope-ai/agentscope-samples/blob/main/LICENSE) [![Python](https://img.shields.io/badge/python-%3E%3D3.10-blue)](https://www.python.org/) [![Docs](https://img.shields.io/badge/docs-AgentScope-blue)](https://doc.agentscope.io/) [![Runtime Docs](https://img.shields.io/badge/docs-AgentScope%20Runtime-red)](https://runtime.agentscope.io/) [![Last Commit](https://img.shields.io/github/last-commit/agentscope-ai/agentscope-samples)](https://github.com/agentscope-ai/agentscope-samples) [[δΈ­ζ–‡README]](README_zh.md) Welcome to the **AgentScope Sample Agents** repository! 🎯 This repository provides **ready-to-use Python sample agents** built on top of: - [AgentScope](https://github.com/agentscope-ai/agentscope) - [AgentScope Runtime](https://github.com/agentscope-ai/agentscope-runtime) The examples cover a wide range of use cases β€” from lightweight command-line agents to **full-stack deployable applications** with both backend and frontend. ------ ## πŸ“– About AgentScope & AgentScope Runtime ### **AgentScope** AgentScope is a multi-agent framework designed to provide a **simple and efficient** way to build **LLM-powered agent applications**. It offers abstractions for defining agents, integrating tools, managing conversations, and orchestrating multi-agent workflows. ### **AgentScope Runtime** AgentScope Runtime is a **comprehensive runtime framework** that addresses two key challenges in deploying and operating agents: 1. **Effective Agent Deployment** – Scalable deployment and management of agents across environments. 2. **Sandboxed Tool Execution** – Secure, isolated execution of tools and external actions. It includes **agent deployment** and **secure sandboxed tool execution**, and can be used with **AgentScope** or other agent frameworks. ------ ## ✨ Getting Started - All samples are **Python-based**. - Samples are organized **by functional use case**. - Some samples use only **AgentScope** (pure Python agents). - Others use **both AgentScope and AgentScope Runtime** to implement **full-stack deployable applications** with frontend + backend. - Full-stack runtime versions have folder names ending with: **`_fullstack_runtime`** > πŸ“Œ **Before running** any example, check its `README.md` for installation and execution instructions. ### Install Requirements - [AgentScope Documentation](https://doc.agentscope.io/) - [AgentScope Runtime Documentation](https://runtime.agentscope.io/) ------ ## 🌳 Repository Structure ```bash β”œβ”€β”€ alias/ # Agent to solve real-world problems β”œβ”€β”€ browser_use/ β”‚ β”œβ”€β”€ agent_browser/ # Pure Python browser agent β”‚ └── browser_use_fullstack_runtime/ # Full-stack runtime version with frontend/backend β”‚ β”œβ”€β”€ deep_research/ β”‚ β”œβ”€β”€ agent_deep_research/ # Pure Python multi-agent research β”‚ └── qwen_langgraph_search_fullstack_runtime/ # Full-stack runtime-enabled research app β”‚ β”œβ”€β”€ games/ β”‚ └── game_werewolves/ # Role-based social deduction game β”‚ β”œβ”€β”€ conversational_agents/ β”‚ β”œβ”€β”€ chatbot/ # Chatbot application β”‚ β”œβ”€β”€ chatbot_fullstack_runtime/ # Runtime-powered chatbot with UI β”‚ β”œβ”€β”€ multiagent_conversation/ # Multi-agent dialogue scenario β”‚ └── multiagent_debate/ # Agents engaging in debates β”‚ β”œβ”€β”€ evaluation/ β”‚ └── ace_bench/ # Benchmarks and evaluation tools β”‚ β”œβ”€β”€ data_juicer_agent/ # Data processing multi-agent system β”œβ”€β”€ sample_template/ # Template for new sample contributions └── README.md ``` ------ ## πŸ“Œ Example List | Category | Example Folder | Uses AgentScope | Use AgentScope Runtime | Description | | ----------------------- |-------------------------------------------------------| --------------- | ------------ |--------------------------------------------------| | **Data Processing** | data_juicer_agent/ | βœ… | ❌ | Multi-agent data processing with Data-Juicer | | **Browser Use** | browser_use/agent_browser | βœ… | ❌ | Command-line browser automation using AgentScope | | | browser_use/browser_use_fullstack_runtime | βœ… | βœ… | Full-stack browser automation with UI & sandbox | | **Deep Research** | deep_research/agent_deep_research | βœ… | ❌ | Multi-agent research pipeline | | | deep_research/qwen_langgraph_search_fullstack_runtime | ❌ | βœ… | Full-stack deep research app | | **Games** | games/game_werewolves | βœ… | ❌ | Multi-agent roleplay game | | **Conversational Apps** | conversational_agents/chatbot_fullstack_runtime | βœ… | βœ… | Chatbot application with frontend/backend | | | conversational_agents/chatbot | βœ… | ❌ | | | | conversational_agents/multiagent_conversation | βœ… | ❌ | Multi-agent dialogue scenario | | | conversational_agents/multiagent_debate | βœ… | ❌ | Agents engaging in debates | | **Evaluation** | evaluation/ace_bench | βœ… | ❌ | Benchmarks with ACE Bench | | **General AI Agent** | alias/ | βœ… | βœ… | Agent application running in sandbox to solve diverse real-world problems | ------ ## 🌟 Featured Examples ### DataJuicer Agent A powerful multi-agent data processing system that leverages Data-Juicer's 200+ operators for intelligent data processing: - **Intelligent Query**: Find suitable operators from 200+ data processing operators - **Automated Pipeline**: Generate Data-Juicer YAML configurations from natural language - **Custom Development**: Create domain-specific operators with AI assistance - **Multiple Retrieval Modes**: LLM-based and vector-based operator matching - **MCP Integration**: Native Model Context Protocol support πŸ“– **Documentation**: [English](data_juicer_agent/README.md) | [δΈ­ζ–‡](data_juicer_agent/README_ZH.md) ### Alias-Agent *Alias-Agent* (short for *Alias*) is designed to serve as an intelligent assistant for tackle diverse and complicated real-world tasks, providing three operational modes for flexible task execution: - **Simple React**: Employs vanilla reasoning-acting loops to iteratively solve problems and execute tool calls. - **Planner-Worker**: Uses intelligent planning to decompose complex tasks into manageable subtasks, with dedicated worker agents handling each subtask independently. - **Built-in Agents**: Leverages specialized agents tailored for specific domains, including *Deep Research Agent* for comprehensive analysis and *Browser-use Agent* for web-based interactions. Beyond being a ready-to-use agent, we envision Alias as a foundational template that can be adapted to different scenarios. πŸ“– **Documentation**: [English](alias/README.md) | [δΈ­ζ–‡](alias/README_ZH.md) ------ ## ℹ️ Getting Help If you: - Need installation help - Encounter issues - Want to understand how a sample works Please: 1. Read the sample-specific `README.md`. 2. File a [GitHub Issue](https://github.com/agentscope-ai/agentscope-samples/issues). 3. Join the community discussions: | [Discord](https://discord.gg/eYMpfnkG8h) | DingTalk | |----------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------| | | | ------ ## 🀝 Contributing We welcome contributions such as: - Bug reports - New feature requests - Documentation improvements - Code contributions See the [Contributing](https://github.com/agentscope-ai/agentscope-samples/blob/main/CONTRIBUTING.md) for details. ------ ## πŸ“„ License This project is licensed under the **Apache 2.0 License** – see the [LICENSE](https://github.com/agentscope-ai/agentscope-samples/blob/main/LICENSE) file for details. ------ ## πŸ”— Resources - [AgentScope Documentation](https://doc.agentscope.io/) - [AgentScope Runtime Documentation](https://runtime.agentscope.io/) - [AgentScope GitHub Repository](https://github.com/agentscope-ai/agentscope) - [AgentScope Runtime GitHub Repository](https://github.com/agentscope-ai/agentscope-runtime) ## Contributors ✨ Thanks goes to these wonderful people ([emoji key](https://allcontributors.org/docs/en/emoji-key)):
Weirui Kuang
Weirui Kuang
🚧 πŸ’» πŸ‘€ πŸ“–		 Osier-Yi
Osier-Yi
🚧 πŸ’» πŸ‘€ πŸ“–		 DavdGao
DavdGao
🚧		 qbc
qbc
🚧		 Lamont Huffman
Lamont Huffman
πŸ’» ⚠️		 Daoyuan Chen
Daoyuan Chen
πŸ’» πŸ’‘		 MeiXin Chen
MeiXin Chen
πŸ’» πŸ’‘
Yilun Huang
Yilun Huang
πŸ’» πŸ’‘
Add your contributions
This project follows the [all-contributors](https://github.com/all-contributors/all-contributors) specification. Contributions of any kind welcome!